JP2003277993A - Method and system for estimating coating film thickness on practical car and recording medium - Google Patents
Method and system for estimating coating film thickness on practical car and recording mediumInfo
- Publication number
- JP2003277993A JP2003277993A JP2002078283A JP2002078283A JP2003277993A JP 2003277993 A JP2003277993 A JP 2003277993A JP 2002078283 A JP2002078283 A JP 2002078283A JP 2002078283 A JP2002078283 A JP 2002078283A JP 2003277993 A JP2003277993 A JP 2003277993A
- Authority
- JP
- Japan
- Prior art keywords
- film thickness
- coating film
- coating
- vehicle
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- C—CHEMISTRY; METALLURGY
- C25—ELECTROLYTIC OR ELECTROPHORETIC PROCESSES; APPARATUS THEREFOR
- C25D—PROCESSES FOR THE ELECTROLYTIC OR ELECTROPHORETIC PRODUCTION OF COATINGS; ELECTROFORMING; APPARATUS THEREFOR
- C25D13/00—Electrophoretic coating characterised by the process
- C25D13/22—Servicing or operating apparatus or multistep processes
-
- C—CHEMISTRY; METALLURGY
- C25—ELECTROLYTIC OR ELECTROPHORETIC PROCESSES; APPARATUS THEREFOR
- C25D—PROCESSES FOR THE ELECTROLYTIC OR ELECTROPHORETIC PRODUCTION OF COATINGS; ELECTROFORMING; APPARATUS THEREFOR
- C25D21/00—Processes for servicing or operating cells for electrolytic coating
- C25D21/12—Process control or regulation
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Automation & Control Theory (AREA)
- Application Of Or Painting With Fluid Materials (AREA)
- Length Measuring Devices With Unspecified Measuring Means (AREA)
Abstract
Description
【０００１】[0001]
【発明の属する技術分野】本発明は、車両モデルベース
での電着塗装解析を実施することなく、電着塗装による
実車の塗膜厚を予測する手法に関する。BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for predicting the coating thickness of an actual vehicle by electrodeposition coating without carrying out an electrodeposition coating analysis based on a vehicle model.
【０００２】[0002]
【従来の技術】電着塗装は、高分子電解質の電気泳動現
象や電気透析現象等を利用した塗装法である。この塗装
は、被塗装物の表面に塗膜が均一に付着し、防食性にも
優れているため、車両ボディや部品といった各種部材の
下塗り塗装として広く用いられている。電着塗装によ
り、部材表面に付着する塗装膜厚を一定の範囲に収める
ことは、防錆対策、塗料消費量の減少、或いは部材軽量
化等の観点から重要な設計課題である。そのため、電着
塗装解析による塗膜析出状態の解析・検討が重要とな
る。従来は、車両形状をメッシュで表現した車両モデル
を用いて、電着塗装解析を行うことによって、実車の塗
膜厚を予測・評価していた。2. Description of the Related Art Electrodeposition coating is a coating method utilizing the electrophoretic phenomenon or electrodialysis phenomenon of a polymer electrolyte. This coating is widely used as an undercoating coating for various members such as vehicle bodies and parts because the coating film is evenly attached to the surface of the object to be coated and has excellent corrosion resistance. Keeping the coating film thickness that adheres to the surface of the member by electrodeposition coating within a certain range is an important design issue from the viewpoint of rust prevention measures, reduction of paint consumption, or weight reduction of the member. Therefore, it is important to analyze and study the state of coating film deposition by electrodeposition coating analysis. Conventionally, the coating thickness of an actual vehicle has been predicted and evaluated by performing electrodeposition coating analysis using a vehicle model in which the vehicle shape is represented by a mesh.
【０００３】[0003]
【発明が解決しようとする課題】しかしながら、電着塗
装解析を車両モデルベースで行う場合には、まず車両形
状をメッシュで表現した解析メッシュを生成する必要が
ある。例えば、車両中の個々の部材の形状をメッシュで
表現した部材メッシュを車両全体に重合・拡張し、全て
の部材を含む実車全体の車両メッシュを生成する。この
場合、車両全体に対して部材メッシュを重ね合わせてい
くため、複雑な車両メッシュのメッシュ数が膨大にな
る。また、車両全体に対する電着塗装解析に要する演算
量も膨大になる。したがって、効率的なメッシュ生成と
解析とを行うためにはコンピュータに高い処理能力が要
求される。しかしながら、一般に普及しているパーソナ
ルコンピュータの処理能力には限界があるため、車両モ
デルの解析メッシュを生成するのに、或いは、車両ベー
スでの塗膜量を予測するのに長時間を要するという問題
がある。However, when the electrodeposition coating analysis is performed on the vehicle model base, it is necessary to first generate an analysis mesh in which the vehicle shape is represented by a mesh. For example, a member mesh in which the shape of each member in the vehicle is expressed by a mesh is overlapped and expanded over the entire vehicle to generate a vehicle mesh for the entire actual vehicle including all the members. In this case, since the member meshes are overlaid on the entire vehicle, the number of complicated vehicle meshes becomes enormous. In addition, the amount of calculation required for the electrodeposition coating analysis for the entire vehicle becomes enormous. Therefore, a computer is required to have a high processing capability in order to perform efficient mesh generation and analysis. However, there is a limit to the processing capacity of the popular personal computer, so it takes a long time to generate the analysis mesh of the vehicle model or to predict the coating amount on the vehicle base. There is.
【０００４】本発明は、かかる事情に鑑みてなされたも
のであり、その目的は、車両モデルベースでの電着塗装
解析を実施しなくても、実車の塗膜厚を予測可能にする
ことである。The present invention has been made in view of such circumstances, and an object thereof is to make it possible to predict the coating film thickness of an actual vehicle without conducting an electrodeposition coating analysis based on the vehicle model. is there.
【０００５】また、本発明の別の目的は、実車の塗膜厚
予測に要する演算量の低減を図り、実車の塗膜厚を効率
的に算出可能にすることである。Another object of the present invention is to reduce the amount of calculation required for predicting the coating film thickness of an actual vehicle so that the coating film thickness of the actual vehicle can be efficiently calculated.
【０００６】[0006]
【課題を解決するための手段】かかる課題を解決するた
めに、第１の発明は、電着塗装ラインを用いて電着塗装
を行おうとする対象車に関して、実車状態の塗膜厚を予
測する方法を提供する。この予測方法は、コンピュータ
を用いて、対象車の一部を構成する構成部材を解析対象
にした電着塗装解析を行い、構成部材の塗膜厚解析値を
算出する第１のステップと、コンピュータが、予め用意
された相関予測式に基づいて、塗膜厚解析値から、対象
車に関する実車状態の塗膜厚を予測する第２のステップ
とを有する。相関予測式は、対象車が電着塗装を行おう
とする電着塗装ラインにおいて既に電着塗装が行われた
量産車に関する実車状態の塗膜厚と、量産車の一部を構
成する構成部材を解析対象にした電着塗装解析より得ら
れる構成部材の塗膜厚解析値との相関関係を規定してい
る。その際、量産車の一部を構成する構成部材と、量産
車の一部を構成する構成部材とを同一にすれば、塗膜厚
の予測精度の向上を図ることができる。In order to solve such a problem, the first invention predicts the coating film thickness in an actual vehicle state with respect to a target vehicle to be subjected to electrodeposition coating using an electrodeposition coating line. Provide a way. In this prediction method, a computer is used to perform an electro-deposition coating analysis targeting the constituent members constituting a part of the target vehicle as an analysis target, and a first step of calculating a coating film thickness analysis value of the constituent members; However, the second step of predicting the coating film thickness of the target vehicle in the actual vehicle state from the coating film thickness analysis value based on the correlation prediction formula prepared in advance. The correlation prediction formula is the coating thickness in the actual vehicle state for a mass-produced vehicle that has already been subjected to electrodeposition coating in the electrodeposition coating line where the target vehicle is going to perform electrodeposition coating, and the components that form part of the mass-production vehicle. It stipulates the correlation with the coating film thickness analysis values of the constituent members obtained by the electrodeposition coating analysis which is the analysis target. At this time, if the constituent members forming a part of the mass-produced vehicle and the constituent members forming a part of the mass-produced vehicle are the same, the accuracy of predicting the coating film thickness can be improved.
【０００７】ここで、上記第２のステップにおいて、相
関予測式として、少なくとも、構成部材の塗膜厚解析値
を入力変数とした関数を用いてもよい。また、相関予測
式として、少なくとも、構成部材の塗膜厚解析値を入力
としたニューラルネットワークを用いてもよい。Here, in the second step, a function having at least the coating film thickness analysis value of the constituent member as an input variable may be used as the correlation prediction formula. Further, as the correlation prediction formula, at least a neural network which inputs the coating film thickness analysis value of the constituent member may be used.
【０００８】また、上記第２のステップは、コンピュー
タが、相関予測式より算出された、対象車に関する実車
状態の塗膜厚に対して、電着設備条件または電着液特性
を考慮した補正を行う第３のステップを含むことが好ま
しい。この場合、第３のステップは、少なくとも電着設
備条件または電着液特性を入力としたニューラルネット
ワークを用いて行うことが望ましい。In the second step, the computer corrects the coating film thickness of the target vehicle in the actual vehicle state calculated by the correlation prediction formula in consideration of the electrodeposition facility condition or the electrodeposition liquid characteristic. It preferably includes a third step of performing. In this case, it is desirable that the third step be performed using at least a neural network with the electrodeposition facility conditions or the electrodeposition liquid characteristics as inputs.
【０００９】また、上記第１のステップは、構成部材に
関して解析メッシュを生成するステップと、解析メッシ
ュに対して、電着液が外部から浸入しない処理を施すス
テップとを含むことが好ましい。It is preferable that the first step includes a step of generating an analysis mesh with respect to the constituent members, and a step of subjecting the analysis mesh to a treatment for preventing the electrodeposition liquid from entering from the outside.
【００１０】第２の発明は、電着塗装ラインを用いて電
着塗装を行おうとする対象車に関して、実車状態の塗膜
厚を予測するシステムを提供する。この予測システム
は、記憶装置とコンピュータとを有する。記憶装置に
は、予測相関式が記憶されている。この予測相関式は、
対象車が電着塗装を行おうとする電着塗装ラインにおい
て既に電着塗装が行われた量産車に関する実車状態の塗
膜厚と、量産車の一部を構成する構成部材を解析対象に
した電着塗装解析より得られる構成部材の塗膜厚解析値
との相関関係を規定している。コンピュータは、対象車
の一部を構成する構成部材を解析対象にした電着塗装解
析を行い、構成部材の塗膜厚解析値を算出する。また、
コンピュータは、相関予測式に基づいて、塗膜厚解析値
から、対象車に関する実車状態の塗膜厚を予測する。そ
の際、量産車の一部を構成する構成部材と、量産車の一
部を構成する構成部材とを同一にすれば、塗膜厚の予測
精度の向上を図ることができる。The second aspect of the present invention provides a system for predicting the coating film thickness in an actual vehicle state with respect to a target vehicle to be subjected to electrodeposition coating using an electrodeposition coating line. The prediction system has a storage device and a computer. A prediction correlation equation is stored in the storage device. This predictive correlation is
The target vehicle is going to perform electrodeposition coating.The coating thickness in the actual vehicle state regarding the mass-produced vehicle that has already been electrodeposited in the electrodeposition coating line and the electrode materials for the components constituting a part of the mass-produced vehicle were analyzed. It stipulates the correlation with the coating film thickness analysis values of the constituent members obtained by coating analysis. The computer performs an electrodeposition coating analysis of the constituent members that form a part of the target vehicle as an analysis target, and calculates a coating film thickness analysis value of the constituent members. Also,
The computer predicts the coating film thickness of the target vehicle in the actual vehicle state from the coating film thickness analysis value based on the correlation prediction formula. At this time, if the constituent members forming a part of the mass-produced vehicle and the constituent members forming a part of the mass-produced vehicle are the same, the accuracy of predicting the coating film thickness can be improved.
【００１１】第３の発明は、電着塗装ラインを用いて電
着塗装を行おうとする対象車に関して、実車状態の塗膜
厚を予測する方法をコンピュータに実行させるプログラ
ムが記録された記録媒体を提供する。この記録媒体に
は、対象車の一部を構成する構成部材を解析対象にした
電着塗装解析を行い、構成部材の塗膜厚解析値を算出す
る第１のステップと、コンピュータが、予め用意された
相関予測式に基づいて、塗膜厚解析値から、対象車に関
する実車状態の塗膜厚を予測する第２のステップとを有
する塗膜厚予測方法をコンピュータに実行させるプログ
ラムが記録されている。ここで、相関予測式は、対象車
が電着塗装を行おうとする電着塗装ラインにおいて既に
電着塗装が行われた量産車に関する実車状態の塗膜厚
と、量産車の一部を構成する構成部材を解析対象にした
電着塗装解析より得られる構成部材の塗膜厚解析値との
相関関係を規定している。ここで、量産車の一部を構成
する構成部材と、量産車の一部を構成する構成部材とを
同一にすれば、塗膜厚の予測精度の向上を図ることがで
きる。A third aspect of the present invention relates to a recording medium having a program recorded thereon for causing a computer to execute a method for predicting a coating film thickness in an actual vehicle state with respect to a vehicle to be subjected to electrodeposition coating using an electrodeposition coating line. provide. This recording medium is prepared in advance by the computer and the first step of performing the electrodeposition coating analysis targeting the constituent members forming a part of the target vehicle and calculating the coating film thickness analysis value of the constituent members. A program for causing a computer to execute a coating film thickness prediction method having a second step of predicting a coating film thickness in an actual vehicle state with respect to a target vehicle based on a coating film thickness analysis value based on the obtained correlation prediction formula is recorded. There is. Here, the correlation prediction formula constitutes a part of the mass production vehicle and the film thickness in the actual vehicle state regarding the mass production vehicle that has already been electrodeposition coated in the electrodeposition coating line where the target vehicle is going to perform electrodeposition coating. It defines the correlation with the coating film thickness analysis value of the constituent member obtained by the electrodeposition coating analysis in which the constituent member is the analysis target. Here, if the constituent members forming a part of the mass-produced vehicle and the constituent members forming a part of the mass-produced vehicle are the same, the accuracy of predicting the coating film thickness can be improved.
【００１２】[0012]
【発明の実施の形態】（システム構成）図１は、本実施
形態に係る実車の塗膜厚予測システムの構成図であり、
このシステムを用いて、電着塗装ラインを用いて電着塗
装を行おうとする実車に関して、実車状態の塗膜厚を予
測する。このシステムは、コンピュータ１０，キーボー
ドやマウス等の入力装置１１，ＣＲＴや液晶ディスプレ
イ等の表示装置１２および磁気ディスク等の記憶装置１
３で構成されている。コンピュータ１０は、ＣＰＵ，Ｒ
ＡＭ，ＲＯＭ，入出力インターフェース等で構成された
周知なものである。このコンピュータ１０は、解析対象
である実車（対象車）の一部を構成するある構成部材
（部材単体または複数部材の組立体）の電着塗装解析を
行うとともに、その解析結果（塗膜厚解析値）に基づ
き、この対象車に関する電着塗装ラインにおける実車レ
ベルの塗膜厚を予測する。オペレータは、表示装置１２
に表示された情報に基づき、入力装置１１を操作して、
解析対象となる構成部材の指定や数値の入力等を行う。DESCRIPTION OF THE PREFERRED EMBODIMENTS (System Configuration) FIG. 1 is a configuration diagram of a coating film thickness prediction system for an actual vehicle according to the present embodiment.
This system is used to predict the coating thickness of an actual vehicle that is going to be electrodeposited using an electrodeposition coating line. This system includes a computer 10, an input device 11 such as a keyboard and a mouse, a display device 12 such as a CRT and a liquid crystal display, and a storage device 1 such as a magnetic disk.
It is composed of three. The computer 10 is a CPU, R
It is a well-known one composed of an AM, a ROM, an input / output interface and the like. The computer 10 performs an electrodeposition coating analysis of a certain constituent member (a single member or an assembly of a plurality of members) that constitutes a part of an actual vehicle (target vehicle) to be analyzed, and the analysis result (coating film thickness analysis). Based on the value), the actual vehicle-level coating thickness in the electrodeposition coating line for this target vehicle is predicted. The operator uses the display device 12
Operate the input device 11 based on the information displayed on
Designate the components to be analyzed and enter numerical values.
【００１３】記憶装置１３には、対象車の一部を構成す
る構成部材をメッシュで表現した部材メッシュデータ、
塗装環境をメッシュ表現したバックグラウンドメッシュ
メッシュ等が記憶されている。これらのデータは、構成
部材ベースでの電着塗装解析を行う際に用いられる。ま
た、記憶装置１３には、後述する相関予測式も記憶され
ており、対象車に関する実車レベルの塗膜厚は、この相
関予測式を用いて、構成部材ベースの解析結果から一義
的に算出される。なお、後述するコンピュータ処理の過
程で生成された電着塗装の解析結果も記憶装置１３に記
憶される。The storage device 13 stores member mesh data in which constituent members forming a part of the target vehicle are expressed by meshes,
A background mesh that represents the painting environment as a mesh is stored. These data are used when performing electrodeposition coating analysis on a component basis. In addition, the storage device 13 also stores a correlation prediction formula described later, and the actual vehicle-level coating film thickness of the target vehicle is uniquely calculated from the analysis result of the component member base using this correlation prediction formula. It The storage device 13 also stores the analysis result of electrodeposition coating generated in the process of computer processing described later.
【００１４】図２は、実車の塗膜厚予測の手順を示すフ
ローチャートである。まず、ステップ１において、対象
車のある構成部材（部材単体または複数部材の組立体）
を解析対象とし、標準塗料を用いた構成部材ベースの電
着塗装解析を行う。この解析結果として、その構成部材
の塗膜厚Ｘ（塗膜厚解析値）が算出される。FIG. 2 is a flow chart showing the procedure for predicting the coating thickness of an actual vehicle. First, in step 1, a component member of a target vehicle (a single member or an assembly of a plurality of members)
The target is the analysis target, and a component member-based electro-deposition coating analysis using standard paint is performed. As the analysis result, the coating film thickness X (coating film thickness analysis value) of the constituent member is calculated.
【００１５】図３は、構成部材ベースの電着塗装解析の
一例を示すフローチャートである。この解析手順自体は
周知なものであるので、概略的に説明する。まず、ステ
ップ１１では初期設定が行われる。このステップでは、
注目している部位(例えば、フロントピラーやセンター
ピラー)の解析メッシュを入力し、境界条件や計算条件
を設定する。構成部材ベースで解析を行うに際して、部
材切断面から電着液が部材組立体内部に浸入するのを防
ぐため、解析対象となる切出した構成部材(テストピー
ス)に対して、計算上の詰め物や蓋等に相当する端面修
正を施しておく。外部からの電着液浸入を阻止する処理
を施すことにより、解析精度の向上を図る。FIG. 3 is a flow chart showing an example of the component member base electrodeposition coating analysis. This analysis procedure itself is well known and will be described briefly. First, in step 11, initial setting is performed. In this step,
Input the analysis mesh of the part of interest (for example, the front pillar or the center pillar) and set the boundary conditions and calculation conditions. When performing analysis on the component member base, in order to prevent the electrodeposition liquid from entering the inside of the member assembly from the member cut surface, the cutout component member (test piece) that is the analysis target is calculated with a filling pad or Modify the end face corresponding to the lid etc. The accuracy of analysis is improved by applying a process to prevent the invasion of the electrodeposition liquid from the outside.
【００１６】ステップ１２では、計算のタイムステップ
をΔtだけ進め、続くステップ１３では、現在の時刻ｔ
における電極電圧等の電位境界条件を更新する。そし
て、有限体積法、有限要素法、或いは有限差分法等によ
り、電位拡散方程式を解いて、電着液槽内の電位分布を
計算する（ステップ１４）。これにより得られた電位分
布に基づいて、部材表面に吸着している塗料の膜厚抵抗
を考慮して部材表面の電流密度を求める（ステップ１
５）。つぎに、予め基礎実験等によって確認しておいた
電流密度と塗膜厚との予測式より、電流密度から、部材
表面における塗膜析出量ΔＸを算出する（ステップ１
６）。続くステップ１７において、従前の塗膜厚Ｘ(１
タイムステップ前の塗膜厚)に今回算出された塗膜析出
量ΔＸを加えることで塗膜厚Ｘを更新する（現在の時刻
ｔにおける塗膜厚に相当）。そして、ステップ１８にお
いて、現在の時刻ｔと解析終了時刻ｔENDとを比較し
て、解析終了であるか否かを判断する。解析終了時刻ｔ
ENDに到達していない場合にはステップ１２に戻り、解
析終了時刻ｔENDに到達するまでステップ１２〜１８の
手順を繰返し実行する。やがて解析終了時刻ｔENDに到
達すると、ステップ１８からステップ１９に進んで塗膜
厚Ｘを出力し、電着塗装解析を終了する。In step 12, the calculation time step is advanced by Δt, and in the following step 13, the current time t.
The potential boundary conditions such as the electrode voltage at are updated. Then, the potential diffusion equation is solved by the finite volume method, the finite element method, the finite difference method or the like to calculate the potential distribution in the electrodeposition liquid tank (step 14). Based on the obtained potential distribution, the current density on the surface of the member is determined in consideration of the film thickness resistance of the paint adsorbed on the surface of the member (step 1).
5). Next, the amount of coating film deposition ΔX on the surface of the member is calculated from the current density according to the prediction formula of the current density and the coating film thickness that has been confirmed in advance by a basic experiment or the like (step 1
6). In the following step 17, the coating thickness X (1
The coating film thickness X is updated by adding the coating film deposition amount ΔX calculated this time to (the coating film thickness before the time step) (corresponding to the coating film thickness at the current time t). Then, in step 18, the current time t is compared with the analysis end time tEND to determine whether or not the analysis has ended. Analysis end time t
If END has not been reached, the process returns to step 12, and the procedure of steps 12 to 18 is repeated until the analysis end time tEND is reached. When the analysis end time tEND is reached, the process proceeds from step 18 to step 19 to output the coating film thickness X and end the electrodeposition coating analysis.
【００１７】図２のステップ１に続くステップ２では、
構成部材ベースの電着塗装解析によって算出された塗膜
厚Ｘから、記憶装置１３中に予め設定された相関予測式
に基づいて、対象車に関する実車状態の塗膜厚Ｙを算出
する。ここで、構成部材ベースとは、対象車全体を解析
対象にするのではなく、対象車の一部を構成する一構成
部材を解析対象することをいう。また、この相関予測式
は、「量産車」に関する実車状態の塗膜厚と、「量産
車」の一部を構成する構成部材の塗膜厚解析値との相関
関係を規定している。ここで、「量産車」とは、対象車
が電着塗装を行おうとする電着塗装ラインにおいて既に
電着塗装が行われた車であり、例えば、前型車や類似車
が挙げられる。すなわち、量産車は、今回塗膜状態を予
測しようとしている実車そのものではなく、同一の電着
塗装ラインで電着塗装が既に行われた車である。また、
量産車の構成部材に関する塗膜厚解析値は、この構成部
材を解析対象に電着塗装解析を行うことにより得られ
る。なお、予測精度の向上を図るために、量産車の構成
部材は、対象車の構成部材と同一部材であることが好ま
しい。In step 2 following step 1 in FIG.
From the coating film thickness X calculated by the constituent member-based electrodeposition coating analysis, the coating film thickness Y of the target vehicle in the actual vehicle state is calculated based on the correlation prediction formula preset in the storage device 13. Here, the component member base means that one component member that constitutes a part of the target vehicle is analyzed, instead of the entire target vehicle being analyzed. In addition, this correlation prediction formula defines the correlation between the coating film thickness in the actual vehicle state relating to the “mass production vehicle” and the coating film thickness analysis value of the constituent members forming a part of the “production vehicle”. Here, the “mass production vehicle” is a vehicle that has already been subjected to electrodeposition coating in the electrodeposition coating line where the target vehicle is going to perform electrodeposition coating, and examples thereof include a front model vehicle and a similar vehicle. That is, the mass-produced vehicle is not the actual vehicle whose coating film state is to be predicted this time, but the vehicle that has already been subjected to electrodeposition coating on the same electrodeposition coating line. Also,
The coating film thickness analysis value regarding the constituent member of the mass-produced vehicle can be obtained by performing the electrodeposition coating analysis on the constituent member as an analysis target. In order to improve the prediction accuracy, it is preferable that the constituent members of the mass-produced vehicle are the same as the constituent members of the target vehicle.
【００１８】相関予測式は、下記の手法１〜２のいずれ
かによって設定される。The correlation prediction formula is set by any of the following methods 1 and 2.
【００１９】（手法１）相関予測式として下式の重相関
関数ｆ（Ｘ，Ｌ，Ａ，Ｈ，・・・）を用いる（Ｘ，Ｌ，
Ａ，Ｈは入力変数、Ｃ0〜Ｃ4は係数）。(Method 1) A multiple correlation function f (X, L, A, H, ...) Of the following equation is used as a correlation prediction equation (X, L,
A and H are input variables, and C0 to C4 are coefficients).
【数１】 Ｙ＝Ｃ0＋Ｃ1・Ｘ＋Ｃ2・Ｌ＋Ｃ3・Ａ＋Ｃ4・Ｈ＋…[Equation 1] Y = C0 + C1 ・ X + C2 ・ L + C3 ・ A + C4 ・ H + ...
【００２０】ここで、変数Ｙは、量産車に関する実車状
態の塗膜厚（塗膜析出量）であり、変数Ｘは、量産車の
一部を構成する構成部材の塗膜析出量（構成部材ベース
の電着塗装解析による塗膜厚）である。また、変数Ｌ
は、予測点と穴(電着穴や構造上の穴)との間の距離、変
数Ｌは、変数Ｌの対象となる穴面積、変数Ｈは部材間距
離である。例えば、図４にように、ある部材に２つの電
着穴と構造上の穴とが形成されている場合、予測点から
３つの穴までの距離Ｌ１，Ｌ２，Ｌ３が入力変数とな
り、３つの穴の面積Ａ１，Ａ２，Ａ３が入力変数とな
る。また、図５に示すように、互いに対向した２つの部
材Ａ，Ｂ間の距離Ｈは、部材Ｂ側の予測点から部材Ａま
での距離として特定される。Here, the variable Y is the coating film thickness (coating film deposition amount) of a mass-produced vehicle in an actual vehicle state, and the variable X is the coating film deposition amount of constituent members which form a part of the mass-produced vehicle (structuring member). It is the film thickness based on the electrodeposition coating analysis of the base). Also, the variable L
Is the distance between the predicted point and the hole (electrodeposited hole or structural hole), the variable L is the hole area targeted by the variable L, and the variable H is the inter-member distance. For example, as shown in FIG. 4, when two electrodeposition holes and a structural hole are formed in a certain member, the distances L1, L2, L3 from the predicted point to the three holes are input variables and the three Areas A1, A2 and A3 of the holes are input variables. Further, as shown in FIG. 5, the distance H between the two members A and B facing each other is specified as the distance from the predicted point on the member B side to the member A.
【００２１】なお、数式１において、塗膜厚Ｘは、必須
の入力変数であるが、それ以外の変数Ｌ，Ａ，Ｋに関し
ては、すべてを入力変数とする必要は必ずしもなく、予
測精度との関係で適宜選択して適用してもよい。In Formula 1, the coating film thickness X is an indispensable input variable, but the variables L, A, and K other than the above need not all be input variables, and the predictive accuracy. You may select suitably according to the relationship and apply.
【００２２】実車状態の塗膜厚Ｙ（塗膜析出量）は、構
成部材ベースの電着塗装解析により算出された構成部材
の塗膜厚Ｘを必須の入力変数とた相関予測式に基づい
て、一義的に算出される。構成部材の塗膜厚Ｘが厚いほ
ど実車の塗膜厚Ｙも厚くなるという関係からわかるよう
に、両変数Ｘ，Ｙの間には明確な相関関係がある。そこ
で、実験やシミュレーション等を通じて、係数Ｃ0〜Ｃ4
の値を適切に設定すれば、構成部材ベースの塗膜厚Ｘか
ら実車の電着塗装ライン上における実車塗膜厚Ｙ（実車
状態の塗膜厚）を予測することが可能となる。The coating film thickness Y in the actual vehicle state (coating film deposition amount) is based on a correlation predicting equation in which the coating film thickness X of the constituent member calculated by the electrodeposition coating analysis of the constituent member is an essential input variable. , Is uniquely calculated. As can be seen from the relationship that the coating film thickness Y of the actual vehicle increases as the coating film thickness X of the constituent member increases, there is a clear correlation between the two variables X and Y. Therefore, through experiments and simulations, the coefficients C0 to C4
If the value of is properly set, it is possible to predict the actual vehicle coating film thickness Y (the actual vehicle coating film thickness) on the actual vehicle electrodeposition coating line from the component member base coating film thickness X.
【００２３】なお、相関予測式は数式１の重相関関数ｆ
の代わりに、入力変数Ｘ1〜Ｘ4と塗膜析出量Ｙとの対応
関係を記述したテーブルであってもよい。また、重相関
関数ｆを予め複数用意しておいて、個々の電着塗装のケ
ースに応じて、適宜のものを選択して適用してもよい。The correlation prediction formula is the multiple correlation function f of the formula 1.
Instead of, the table may describe a correspondence relationship between the input variables X1 to X4 and the coating film deposition amount Y. Alternatively, a plurality of multiple correlation functions f may be prepared in advance, and an appropriate one may be selected and applied according to each case of electrodeposition coating.
【００２４】（第２のケース）相関予測式としてニュー
ラルネットワークを利用する。図６は、一般的なニュー
ラルネットワークの基本構成を示す図である。入力層、
中間層および出力層からなる階層型ニューラルネットワ
ークにおいて、それぞれの層は、同一機能を有する複数
の素子で構成されている。それぞれの素子は、固有の重
み係数ｗijで結合されている。(Second case) A neural network is used as a correlation prediction equation. FIG. 6 is a diagram showing a basic configuration of a general neural network. Input layer,
In a hierarchical neural network including an intermediate layer and an output layer, each layer is composed of a plurality of elements having the same function. Each element is combined with a unique weighting factor wij.
【００２５】図７は、素子の内部構造の説明図である。
それぞれの素子は、入力データｙiに対して数式２，３
に示す計算を行い、その演算結果を出力データＹjして
出力する。ここで、ｗijは、ｉ番目の素子とｊ番目の素
子との間の重み係数であり、θjはしきい値である。FIG. 7 is an explanatory diagram of the internal structure of the element.
Each element has the following equations 2 and 3 for the input data yi.
The calculation shown in is performed, and the calculation result is output as output data Yj. Here, wij is a weighting coefficient between the i-th element and the j-th element, and θj is a threshold value.
【数２】 [Equation 2]
【数３】 [Equation 3]
【００２６】数式３は、シグモイド関数と呼ばれ、ニュ
ーラルネットワーク素子の関数として一般的に用いられ
ている。図８は、シグモイド関数の入出力特性図であ
る。この特性図からわかるように、シグモイド関数は０
から１まで連続的に変化し、しきい値θjが小さくなる
につれて、ステップ関数に近づいていく。Equation 3 is called a sigmoid function, and is generally used as a function of a neural network element. FIG. 8 is an input / output characteristic diagram of the sigmoid function. As can be seen from this characteristic diagram, the sigmoid function is 0
It continuously changes from 1 to 1 and approaches a step function as the threshold value θj becomes smaller.
【００２７】ニューラルネットワークによる推定結果の
精度向上を図るためには、重み係数ｗijとしきい値θj
とを適切に調整する必要がある。この調整（学習ともい
う）は、Back-Propagation法と呼ばれる手法を用いて行
う。これは、学習するための教師用データを予め用意
し、結果が教師用データと一致するように学習を進め、
重み係数ｗijとしきい値θjとを決定する方法である。
重み係数ｗijとしきい値θjとの初期値は、ともに乱数
で与える。入力データをニューラルネットワークの入力
層素子に入力し、出力層素子からの出力結果を教師用デ
ータの値と比較し、下記の数式４で表される誤差Ｅを算
出する。ここで、Ｙkは、ニューラルネットワーク出力
素子の出力値、Ｄkは望ましい出力値、ｎは教師用デー
タ数である。In order to improve the accuracy of the estimation result by the neural network, the weighting factor wij and the threshold value θj.
And need to be adjusted appropriately. This adjustment (also referred to as learning) is performed using a method called Back-Propagation method. This prepares teacher data for learning in advance and advances learning so that the results match the teacher data.
This is a method of determining the weighting factor wij and the threshold value θj.
Initial values of the weighting factor wij and the threshold value θj are both given by random numbers. The input data is input to the input layer element of the neural network, the output result from the output layer element is compared with the value of the teacher data, and the error E represented by the following formula 4 is calculated. Here, Yk is an output value of the neural network output element, Dk is a desired output value, and n is the number of teacher data.
【数４】 [Equation 4]
【００２８】つぎに、数式５により算出された誤差Ｅに
対する各重み係数ｗij、しきい値の寄与率∂Ｅ/∂ｗi
j，∂Ｅ/∂θjを求め、数式５，６に基づき、各重み係
数の変化量Δｗij(t+1)、しきい値の変化量Δθj(t+1)
を算出する。Next, each weighting coefficient wij and the threshold contribution rate ∂E / ∂wi with respect to the error E calculated by the equation (5).
j, ∂E / ∂θj are calculated, and the change amount Δwij (t + 1) of each weighting coefficient and the change amount Δθj (t + 1) of the threshold value are calculated based on Formulas 5 and 6.
To calculate.
【数５】 [Equation 5]
【数６】 [Equation 6]
【００２９】ここで、α，β，γ，εは定数であり、α
＝γ＝0.1，β＝ε＝0.9とする。また、Δｗij(t)は１
学習前の重み係数の修正量であり、Δθj(t)は、１学習
前のしきい値の修正量である。上述した重み係数ｗij，
しきい値θjに対する修正を繰り返して学習を進める。
学習回数は、１教師データ当たり500回以上とする。Where α, β, γ and ε are constants, and α
= Γ = 0.1 and β = ε = 0.9. Also, Δwij (t) is 1
The correction amount of the weight coefficient before learning, and Δθj (t) is the correction amount of the threshold value before learning. The above weighting factors wij,
The learning is advanced by repeatedly correcting the threshold value θj.
The number of learning times is 500 or more per teacher data.
【００３０】図９は、実車の塗膜厚Ｙを予測するニュー
ラルネットワークの構成図である。同図に示した３層モ
デルのように、入力層の素子数は２つ以上必要であり、
構成部材ベースの解析結果である塗膜厚Ｘ以外に、予測
点と穴(電着穴や構造上の穴)との距離Ｌ、Ｌの対象とな
る穴面積Ａ、部材間距離Ｈ等を設定する。なお、上述し
た手法１と同様に、距離Ｌ、穴面積Ａ、部材間距離Ｈの
すべてを入力とする必要は必ずしもなく、必要に応じて
適宜の変数を適用すればよい。また、中間層の素子数に
関しては、理論的に求める方法がないため、中間層の素
子数を変えた場合に推定精度がどのように変化するかを
調べた上で適切な数を設定する。出力層の素子からの出
力が実車レベルの塗膜厚Ｙ（塗膜析出量）に相当する。FIG. 9 is a block diagram of a neural network for predicting the coating film thickness Y of an actual vehicle. Like the three-layer model shown in the figure, the number of elements in the input layer must be two or more,
In addition to the coating film thickness X, which is the analysis result of the component member base, set the distance L between the predicted point and the hole (electrodeposition hole or structural hole), the hole area A targeted for L, the distance H between members, etc. To do. Note that, similarly to the above-described method 1, it is not always necessary to input all of the distance L, the hole area A, and the member-to-member distance H, and an appropriate variable may be applied as necessary. In addition, as for the number of elements in the intermediate layer, there is no theoretical method, so an appropriate number is set after investigating how the estimation accuracy changes when the number of elements in the intermediate layer is changed. The output from the element of the output layer corresponds to the actual vehicle-level coating film thickness Y (coating film deposition amount).
【００３１】この手法２では、ステップ１の電着塗装解
析で算出された部材塗膜厚Ｘを必須の入力とし、かつ、
距離Ｌ、穴面積Ａ、部材間距離Ｈを適宜入力としたニュ
ーラルネットワークを用いて、実車塗膜厚Ｙを求めてい
る。非線形的な現象の予測に適したニューラルネットワ
ークを用いることで、手法１の重相関関数ｆを用いる場
合と比べて、実車塗膜厚Ｙの予測精度を向上させること
ができる。In this method 2, the member coating film thickness X calculated by the electrodeposition coating analysis in step 1 is made an essential input, and
The actual vehicle coating film thickness Y is obtained by using a neural network in which the distance L, the hole area A, and the member-to-member distance H are appropriately input. By using a neural network suitable for predicting a non-linear phenomenon, it is possible to improve the prediction accuracy of the actual vehicle coating film thickness Y as compared with the case where the multiple correlation function f of the method 1 is used.
【００３２】ステップ３では、ステップ２で得られた実
車塗膜厚Ｙを必要に応じて補正する。ここでは、電圧パ
ターンや塗料特性との差異等を考慮した多次元関数やニ
ューラルネットワーク等により補正値を求め、この補正
値を用いて塗膜厚Ｙを補正する。図１０は、補正値算出
用ニューラルネットワークの構成図である。入力として
は、電着塗装の最大電圧（Ｍａｘ電圧）、電圧パター
ン、設備稼働状況等の電着設備条件と、塗料液温、塗料
特性等の電着液特性とを含む。このように、電着設備条
件や電着液特性等を入力としたニューラルネットワーク
を適用すれば、実状に適した最適な補正値を見出せ、電
着設備条件や電着液が変わった場合にも適用することが
できる。In step 3, the actual vehicle coating film thickness Y obtained in step 2 is corrected if necessary. Here, a correction value is obtained by a multidimensional function, a neural network, or the like that takes into consideration the difference between the voltage pattern and the paint characteristics, and the coating film thickness Y is corrected using this correction value. FIG. 10 is a configuration diagram of a correction value calculation neural network. The input includes the electrodeposition facility conditions such as the maximum voltage (Max voltage) of the electrodeposition coating (Max voltage), the voltage pattern, the facility operating status, and the electrodeposition liquid characteristics such as the coating liquid temperature and the coating characteristics. In this way, by applying a neural network that inputs the conditions for electrodeposition equipment and the characteristics of the electrodeposition solution, it is possible to find the optimum correction value that is suitable for the actual situation, and even when the conditions for electrodeposition equipment or the electrodeposition solution change. Can be applied.
【００３３】また、相関予測式としてニューラルネット
ワークを用い、かつ、補正値用のニューラルネットワー
クを用いる場合、図１１に示すような単一化したニュー
ラルネットワーク構成にしてもよい。この場合、入力
は、構成部材の塗膜厚Ｘ、部材間距離Ｈ、距離Ｌ、穴面
積Ａに、電着設備条件と塗料特性とを付加した形態にな
る。このような構成にすれば、予測精度の高い実車塗膜
厚Ｙを一度に求めることができ、ステップ３の補正処理
が不要になる。When a neural network is used as the correlation prediction equation and a neural network for correction values is used, a unified neural network configuration as shown in FIG. 11 may be used. In this case, the input is in a form in which the electrodeposition facility conditions and the paint characteristics are added to the coating film thickness X of the constituent members, the member distance H, the distance L, and the hole area A. With such a configuration, the actual vehicle coating film thickness Y with high prediction accuracy can be obtained at one time, and the correction process of step 3 becomes unnecessary.
【００３４】そして、ステップ３に続くステップ４にお
いて補正された実車塗膜厚Ｙを出力し、処理を終了す
る。Then, in step 4 following step 3, the corrected actual vehicle coating film thickness Y is output, and the process ends.
【００３５】本実施形態では、注目している構成部材の
解析メッシュを用いて、この構成部材の電着塗装解析を
行い、構成部材レベルの塗膜厚Ｘを算出する。構成部材
レベルの塗膜厚Ｘと車両レベルの塗膜厚Ｙとは相関関係
にある。したがって、実験やシミュレーション等を通じ
て、両者の関係を相関予測式として事前に求めておけ
ば、車両モデルベースでの電着塗装解析を実施しなくて
も、実際の電着塗装ライン上における実車塗膜厚Ｙを効
率的に予測することが可能となる。In the present embodiment, the analysis mesh of the component of interest is used to perform electrodeposition coating analysis of this component to calculate the coating film thickness X at the component level. The coating film thickness X at the component member level and the coating film thickness Y at the vehicle level have a correlation. Therefore, if the relationship between the two is obtained in advance as a correlation prediction formula through experiments, simulations, etc., the actual vehicle paint film on the actual electrodeposition coating line can be obtained without performing the vehicle model-based electrodeposition coating analysis. It is possible to efficiently predict the thickness Y.
【００３６】また、複雑な車両モデルの解析メッシュを
生成する必要はなく、車両モデルベースでの電着塗装解
析を行う必要もない。演算量が比較的少ない構成部材ベ
ースでの電着塗装解析を行えば、実車レベルの塗膜厚Ｙ
を迅速に算出することができる。したがって、処理能力
がそれほど高くないパーソナルコンピュータでも、実車
の塗膜厚Ｙを効率的に予測することが可能となる。Further, it is not necessary to generate an analysis mesh of a complicated vehicle model, and it is not necessary to perform the electrodeposition coating analysis based on the vehicle model. If the electrodeposition coating analysis is performed on the component member base with a relatively small amount of calculation, the actual vehicle-level coating film thickness Y
Can be calculated quickly. Therefore, it becomes possible to efficiently predict the coating film thickness Y of an actual vehicle even with a personal computer having a not so high processing capacity.
【００３７】さらに、部材単体の電着塗装試験を実施す
る必要がないので、コストダウンと時間短縮とを図るこ
とができる。特に、本実施形態では、解析対象となる対
象車に先行して、同一の電着塗装ラインによって電着塗
装された量産車に関して、既に蓄積されているデータを
用いて、相関予測式を設定する。この相関予測式は、対
象となる電着塗装ライン固有の特性（例えば、塗料の流
れ、電極の位置等）を良好に反映している。したがっ
て、先行して実際に電着塗装が行われた量産車に関する
相関予測式を、それと同一の電着塗装ラインで電着塗装
を行おうとする対象車に適用すれば、その対象車に関す
る実車状態の塗膜厚を良好に予測することができる。そ
の際、対象車の構成部材と量産車の構成部材とを同一に
すれば、塗膜厚の予測精度を一層向上させることができ
る。Further, since it is not necessary to carry out the electrodeposition coating test for the individual members, cost reduction and time reduction can be achieved. In particular, in the present embodiment, the correlation prediction formula is set using the data that has already been accumulated for the mass-produced vehicles that have been electrodeposition coated by the same electrodeposition coating line prior to the target vehicle that is the analysis target. . This correlation prediction formula favorably reflects the characteristics peculiar to the target electrodeposition coating line (eg, paint flow, electrode position, etc.). Therefore, if the correlation prediction formula for a mass-produced vehicle that was actually electrodeposited in advance is applied to the target vehicle that is going to perform electrodeposition coating on the same electrodeposition coating line, the actual vehicle state related to that target vehicle The coating thickness of can be predicted well. At that time, if the constituent members of the target vehicle and the constituent members of the mass-produced vehicle are made the same, the accuracy of predicting the coating film thickness can be further improved.
【００３８】なお、対象車と量産車との構造上の相違
は、相関予測式には反映できないため、構造上の相違に
起因した塗膜厚は相関予測式自体では評価できない。し
かしながら、本実施形態では、相関予測式の入力変数Ｘ
を、対象車の構成部材を解析対象にした電着塗装解析よ
り算出している。この入力変数Ｘは、対象車と量産車と
の間における構造上の相違を反映している。これによ
り、異車種の蓄積データより特定された相関予測式であ
っても、対象車に関する実車状態の塗膜厚を精度よく検
出することができる。Since the structural difference between the target vehicle and the mass-produced vehicle cannot be reflected in the correlation prediction formula, the coating film thickness due to the structural difference cannot be evaluated by the correlation prediction formula itself. However, in the present embodiment, the input variable X of the correlation prediction formula is
Is calculated from the electrodeposition coating analysis in which the constituent members of the target vehicle are analyzed. This input variable X reflects the structural difference between the target vehicle and the mass-produced vehicle. Accordingly, even with the correlation prediction formula specified from the accumulated data of different vehicle types, it is possible to accurately detect the coating film thickness of the target vehicle in the actual vehicle state.
【００３９】なお、上述した実施形態の機能を実現する
コンピュータプログラムを記録した記録媒体を、図１の
ような構成を有するシステムに対して供給してもよい。
この場合、このシステム中のコンピュータ１が、記録媒
体に格納されたコンピュータプログラムを読み取り実行
することによって、本発明の目的を達成することができ
る。したがって、記録媒体から読み取られたコンピュー
タプログラム自体が本発明の新規な機能を実現するた
め、そのプログラムを記録した記録媒体が本発明を構成
する。コンピュータプログラムを記録した記録媒体とし
ては、例えば、ＣＤ−ＲＯＭ、フレキシブルディスク、
ハードディスク、メモリカード、光ディスク、ＤＶＤ−
ＲＯＭ、ＤＶＤ−ＲＡＭ等が挙げられる。また、上述し
た実施形態の機能を実現するコンピュータプログラム自
体も新規な機能を有している。A recording medium recording a computer program that realizes the functions of the above-described embodiments may be supplied to the system having the configuration shown in FIG.
In this case, the computer 1 in this system can achieve the object of the present invention by reading and executing the computer program stored in the recording medium. Therefore, since the computer program itself read from the recording medium realizes the novel function of the present invention, the recording medium recording the program constitutes the present invention. Examples of the recording medium recording the computer program include a CD-ROM, a flexible disk,
Hard disk, memory card, optical disk, DVD-
ROM, DVD-RAM, etc. are mentioned. Further, the computer program itself that realizes the functions of the above-described embodiments also has new functions.
【００４０】[0040]
【発明の効果】本発明では、車両モデルベースでの電着
塗装解析を行わなくても、着目している構成部材の電着
塗装解析結果から実車の塗膜厚を一義的に算出する。し
たがって、車両モデルの解析メッシュを生成したり、車
両モデルベースでの電着塗装解析を行う必要がないの
で、少ない演算量で実車の塗膜厚を効率的に予測するこ
とが可能となる。According to the present invention, the coating film thickness of the actual vehicle is uniquely calculated from the result of the electrodeposition coating analysis of the component of interest without conducting the electrodeposition coating analysis based on the vehicle model. Therefore, it is not necessary to generate the analysis mesh of the vehicle model or to perform the electrodeposition coating analysis based on the vehicle model, so that the coating thickness of the actual vehicle can be efficiently predicted with a small amount of calculation.
【図１】実車の塗膜厚予測システムの構成図[Fig. 1] Configuration diagram of coating thickness prediction system for actual vehicle
【図２】実車の塗膜厚予測手順を示すフローチャートFIG. 2 is a flowchart showing a coating film thickness prediction procedure for an actual vehicle.
【図３】構成部材ベースの電着塗装解析のフローチャー
ト[Fig. 3] Flow chart of component-based electrodeposition coating analysis
【図４】相関予測式における入力変数の説明図FIG. 4 is an explanatory diagram of input variables in a correlation prediction formula.
【図５】相関予測式における入力変数の説明図FIG. 5 is an explanatory diagram of input variables in the correlation prediction formula.
【図６】一般的なニューラルネットワークの基本構成を
示す図FIG. 6 is a diagram showing a basic configuration of a general neural network.
【図７】素子の内部構造の説明図FIG. 7 is an explanatory diagram of the internal structure of the element.
【図８】シグモイド関数の入出力特性図FIG. 8: Input / output characteristic diagram of sigmoid function
【図９】実車の塗膜厚を予測するニューラルネットワー
クの構成図FIG. 9 is a configuration diagram of a neural network that predicts the coating thickness of an actual vehicle.
【図１０】補正値算出用ニューラルネットワークの構成
図FIG. 10 is a block diagram of a correction value calculation neural network.
【図１１】単一化したニューラルネットワークの構成図FIG. 11 is a block diagram of a unified neural network.
１０ コンピュータ １１ 入力装置 １２ 表示装置 １３ 記憶装置 10 computers 11 Input device 12 Display 13 Storage device
Claims (9)
とする対象車に関して、実車状態の塗膜厚を予測する方
法において、 コンピュータを用いて、前記対象車の一部を構成する構
成部材を解析対象にした電着塗装解析を行い、前記構成
部材の塗膜厚解析値を算出する第１のステップと、 コンピュータが、予め用意された相関予測式に基づい
て、前記塗膜厚解析値から、前記対象車に関する実車状
態の塗膜厚を予測する第２のステップとを有し、 前記相関予測式は、前記対象車が電着塗装を行おうとす
る電着塗装ラインにおいて既に電着塗装が行われた量産
車に関する実車状態の塗膜厚と、前記量産車の一部を構
成する前記構成部材を解析対象にした電着塗装解析より
得られる前記構成部材の塗膜厚解析値との相関関係を規
定していることを特徴とする実車の塗膜厚予測方法。1. A method of predicting a coating film thickness in an actual vehicle state of a target vehicle to be subjected to electrodeposition coating using an electrodeposition coating line, comprising a computer to constitute a part of the target vehicle. The first step of performing the electrodeposition coating analysis with the member as an analysis target and calculating the coating film thickness analysis value of the constituent member, and the computer based on the correlation prediction formula prepared in advance, the coating film thickness analysis A second step of predicting a coating film thickness of the target vehicle in the actual vehicle state from the value, and the correlation prediction formula is such that in the electrodeposition coating line in which the target vehicle intends to perform electrodeposition coating, A coating film thickness of an actual vehicle related to a coated mass-produced vehicle, and a coating film thickness analysis value of the constituent member obtained by electrodeposition coating analysis in which the constituent member forming a part of the mass-produced vehicle is analyzed. Stipulate the correlation of Vehicle of the coating film thickness prediction method characterized.
は、前記量産車の一部を構成する前記構成部材と同一で
あることを特徴とする請求項１に記載された実車の塗膜
厚予測方法。2. The coating of an actual vehicle according to claim 1, wherein the constituent member forming a part of the mass production vehicle is the same as the constituent member forming a part of the mass production vehicle. Film thickness prediction method.
測式として、少なくとも、前記構成部材の塗膜厚解析値
を入力変数とした関数を用いることを特徴とする請求項
１または２に記載された実車の塗膜厚予測方法。3. The method according to claim 1, wherein in the second step, at least a function having an input variable of a coating film thickness analysis value of the constituent member is used as the correlation prediction formula. A method for predicting coating film thickness of actual vehicles
測式として、少なくとも、前記構成部材の塗膜厚解析値
を入力としたニューラルネットワークを用いることを特
徴とする請求項１または２に記載された実車の塗膜厚予
測方法。4. The neural network in which at least the coating film thickness analysis value of the constituent member is used as the correlation predicting equation in the second step. A method for predicting coating film thickness of actual vehicles
前記相関予測式より算出された、前記対象車に関する実
車状態の塗膜厚に対して、電着設備条件または電着液特
性を考慮した補正を行う第３のステップを含むことを特
徴とする請求項１から４のいずれかに記載された実車の
塗膜厚予測方法。5. The computer according to the second step,
A third step of performing a correction in consideration of an electrodeposition facility condition or an electrodeposition liquid property, with respect to a coating film thickness of the target vehicle in an actual vehicle state calculated by the correlation prediction formula, Item 5. A method for predicting a coating film thickness of an actual vehicle according to any one of items 1 to 4.
備条件または電着液特性を入力としたニューラルネット
ワークを用いて行うことを特徴とする請求項５に記載さ
れた実車の塗膜厚予測方法。6. The coating thickness prediction of an actual vehicle according to claim 5, wherein the third step is performed using a neural network in which at least electrodeposition equipment conditions or electrodeposition liquid characteristics are input. Method.
と、 前記解析メッシュに対して、電着液が外部から浸入しな
い処理を施すステップとを含むことを特徴とする請求項
１から６のいずれかに記載された実車の塗膜厚予測方
法。7. The first step includes: a step of generating an analysis mesh for the constituent member; and a step of subjecting the analysis mesh to a process in which an electrodeposition liquid does not enter from the outside. The coating film thickness prediction method for an actual vehicle according to any one of claims 1 to 6.
とする対象車に関して、実車状態の塗膜厚を予測するシ
ステムにおいて、 前記対象車が電着塗装を行おうとする電着塗装ラインに
おいて既に電着塗装が行われた量産車に関する実車状態
の塗膜厚と、前記量産車の一部を構成する構成部材を解
析対象にした電着塗装解析より得られる前記構成部材の
塗膜厚解析値との相関関係を規定した相関予測式を記憶
した記憶装置と、 前記対象車の一部を構成する構成部材を解析対象にした
電着塗装解析を行い、前記構成部材の塗膜厚解析値を算
出するとともに、前記相関予測式に基づいて、前記塗膜
厚解析値から、前記対象車に関する実車状態の塗膜厚を
予測するコンピュータとを有することを特徴とする実車
の塗膜厚予測システム。8. A system for predicting a coating film thickness of an actual vehicle for a target vehicle to be electrodeposited using an electrodeposition coating line, wherein the target vehicle is to perform electrodeposition coating In the actual vehicle state regarding the mass-produced vehicle that has already been electrodeposited, the coating thickness of the above-mentioned constituent members obtained by the electrodeposition coating analysis of the constituent members that form a part of the above-mentioned mass-produced vehicle A storage device that stores a correlation prediction formula that defines the correlation with the analysis value, and performs an electrodeposition coating analysis that analyzes the constituent members that form a part of the target vehicle as an analysis target, and analyzes the coating film thickness of the constituent members. And a computer for predicting a coating film thickness in an actual vehicle state related to the target vehicle from the coating film thickness analysis value based on the correlation prediction formula, and a coating film thickness prediction for an actual vehicle. system.
とする対象車に関して、実車状態の塗膜厚を予測する方
法をコンピュータに実行させるプログラムが記録された
記録媒体において、 前記対象車の一部を構成する構成部材を解析対象にした
電着塗装解析を行い、前記構成部材の塗膜厚解析値を算
出する第１のステップと、 コンピュータが、予め用意された相関予測式に基づい
て、前記塗膜厚解析値から、前記対象車に関する実車状
態の塗膜厚を予測する第２のステップとを有し、 前記相関予測式は、前記対象車が電着塗装を行おうとす
る電着塗装ラインにおいて既に電着塗装が行われた量産
車に関する実車状態の塗膜厚と、前記量産車の一部を構
成する前記構成部材を解析対象にした電着塗装解析より
得られる前記構成部材の塗膜厚解析値との相関関係を規
定していることを特徴とする実車の塗膜厚予測方法をコ
ンピュータに実行させるプログラムが記録された記録媒
体。9. A recording medium in which a program for causing a computer to execute a method of predicting a coating film thickness of an actual vehicle is recorded, regarding the vehicle to be subjected to electrodeposition coating using an electrodeposition coating line, The first step of performing electrodeposition coating analysis targeting the constituent members constituting a part of the above, and calculating the coating film thickness analysis value of the constituent members, and the computer based on the correlation prediction formula prepared in advance. And a second step of predicting a coating film thickness of the target vehicle in an actual vehicle state from the coating film thickness analysis value, wherein the correlation prediction formula is an electric power that the target vehicle attempts to perform electrodeposition coating. The coating film thickness in the actual vehicle state regarding a mass-produced vehicle that has already been subjected to electrodeposition coating in the coating line, and the above-mentioned constituent members obtained by the electrodeposition coating analysis in which the constituent members forming a part of the mass-produced vehicle are analyzed. Coating thickness solution Recording medium on which the program for executing the film thickness prediction method of the actual vehicle to a computer, characterized in that defines the correlation between the values have been recorded.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2002078283A JP4220169B2 (en) | 2002-03-20 | 2002-03-20 | Actual vehicle coating thickness prediction method, actual vehicle coating thickness prediction system, and recording medium |
| EP03006134.5A EP1351035B1 (en) | 2002-03-20 | 2003-03-18 | Paint film thickness predicting method, system, and recording medium |
| US10/390,716 US6816756B2 (en) | 2002-03-20 | 2003-03-19 | Paint film thickness predicting method and system for actual car, and recording medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2002078283A JP4220169B2 (en) | 2002-03-20 | 2002-03-20 | Actual vehicle coating thickness prediction method, actual vehicle coating thickness prediction system, and recording medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JP2003277993A true JP2003277993A (en) | 2003-10-02 |
| JP4220169B2 JP4220169B2 (en) | 2009-02-04 |
Family
ID=28035568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2002078283A Expired - Fee Related JP4220169B2 (en) | 2002-03-20 | 2002-03-20 | Actual vehicle coating thickness prediction method, actual vehicle coating thickness prediction system, and recording medium |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US6816756B2 (en) |
| EP (1) | EP1351035B1 (en) |
| JP (1) | JP4220169B2 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017066486A (en) * | 2015-09-30 | 2017-04-06 | 富士重工業株式会社 | Flow simulation method of coating |
| CN116770395A (en) * | 2023-08-22 | 2023-09-19 | 深圳市互成自动化设备有限公司 | Electrophoretic powder spraying coating quality monitoring method and system |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7171394B2 (en) * | 2003-10-30 | 2007-01-30 | Ford Motor Company | Global paint process optimization |
| US7346474B2 (en) * | 2004-06-02 | 2008-03-18 | Fuji Jukogyo Kabushiki Kaisha | Method of analyzing residual fluid and computer readable medium |
| US20060031027A1 (en) * | 2004-08-03 | 2006-02-09 | Alman David H | Method and apparatus for predicting properties of a chemical mixture |
| US7606671B2 (en) * | 2007-12-12 | 2009-10-20 | Elcometer, Inc. | Method of quantifying paint and bodywork on automobiles and other painted objects using coating thickness gauges |
| US8244481B2 (en) * | 2009-12-09 | 2012-08-14 | Toyota Motor Engineering & Manufacturing North America, Inc. | Methods for utilizing paint formulations based on paint component risk scores |
| US8775341B1 (en) | 2010-10-26 | 2014-07-08 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
| US9015093B1 (en) | 2010-10-26 | 2015-04-21 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
| EP3330411A1 (en) * | 2016-12-02 | 2018-06-06 | Elsyca N.V. | Intelligent volume meshing for modelling electrochemical processes |
| CN110108245B (en) * | 2019-05-22 | 2021-04-13 | 优信拍（北京）信息科技有限公司 | Method, device and equipment for detecting vehicle paint surface condition |
| CN114829065A (en) * | 2019-11-27 | 2022-07-29 | 3M创新有限公司 | Robot repair control system and method |
| CN111926367B (en) * | 2020-08-25 | 2021-10-22 | 一汽解放青岛汽车有限公司 | Method, device, system, equipment and medium for determining electrophoresis process parameters |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3861471D1 (en) * | 1987-02-10 | 1991-02-14 | Mazda Motor | COATING PROCESS. |
| US5674562A (en) * | 1990-06-25 | 1997-10-07 | Lanxide Technology Company, Lp | Method for making self supporting composite bodies |
| JPH0559593A (en) * | 1991-08-28 | 1993-03-09 | Kansai Paint Co Ltd | Electrodeposition coating method |
| US5366690A (en) * | 1993-06-18 | 1994-11-22 | Combustion Engineering, Inc. | Zirconium alloy with tin, nitrogen, and niobium additions |
| US6185472B1 (en) * | 1995-12-28 | 2001-02-06 | Kabushiki Kaisha Toshiba | Semiconductor device manufacturing method, manufacturing apparatus, simulation method and simulator |
| US5941825A (en) * | 1996-10-21 | 1999-08-24 | Philipp Lang | Measurement of body fat using ultrasound methods and devices |
| WO1998022801A1 (en) * | 1996-11-22 | 1998-05-28 | Autospect, Inc. | Physical parameter measuring apparatus and method thereof |
| US6128081A (en) * | 1996-11-22 | 2000-10-03 | Perceptron, Inc. | Method and system for measuring a physical parameter of at least one layer of a multilayer article without damaging the article and sensor head for use therein |
| ATE297266T1 (en) * | 1999-03-10 | 2005-06-15 | Ishikawajima Harima Heavy Ind | METHOD FOR PRODUCING HOT ROLLED STEEL SHEET |
| US6519037B2 (en) * | 1999-12-23 | 2003-02-11 | Lj Laboratories, Llc | Spectrometer having optical unit including a randomized fiber optic implement |
| US6219138B1 (en) * | 2000-01-10 | 2001-04-17 | The United States Of America As Represented By The Secretary Of The Navy | Particle sizing technique |
| JP3879384B2 (en) * | 2000-03-31 | 2007-02-14 | 株式会社日立製作所 | Method of providing information for predicting thinning, computer-readable recording medium in which a program for predicting thinning is recorded, and method for planning a piping work plan |
| JP4554037B2 (en) * | 2000-07-04 | 2010-09-29 | 東京エレクトロン株式会社 | Consumable consumption level prediction method and deposited film thickness prediction method |
-
2002
- 2002-03-20 JP JP2002078283A patent/JP4220169B2/en not_active Expired - Fee Related
-
2003
- 2003-03-18 EP EP03006134.5A patent/EP1351035B1/en not_active Expired - Fee Related
- 2003-03-19 US US10/390,716 patent/US6816756B2/en not_active Expired - Fee Related
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017066486A (en) * | 2015-09-30 | 2017-04-06 | 富士重工業株式会社 | Flow simulation method of coating |
| CN116770395A (en) * | 2023-08-22 | 2023-09-19 | 深圳市互成自动化设备有限公司 | Electrophoretic powder spraying coating quality monitoring method and system |
| CN116770395B (en) * | 2023-08-22 | 2023-10-20 | 深圳市互成自动化设备有限公司 | Electrophoretic powder spraying coating quality monitoring method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| EP1351035A3 (en) | 2011-05-18 |
| EP1351035A2 (en) | 2003-10-08 |
| US6816756B2 (en) | 2004-11-09 |
| US20030182006A1 (en) | 2003-09-25 |
| JP4220169B2 (en) | 2009-02-04 |
| EP1351035B1 (en) | 2018-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111178385B (en) | Target tracking method for robust online multi-sensor fusion | |
| JP4220169B2 (en) | Actual vehicle coating thickness prediction method, actual vehicle coating thickness prediction system, and recording medium | |
| Momennejad et al. | Predicting the future with multi-scale successor representations | |
| CN111753952A (en) | Learning parameters of a probabilistic model including a Gaussian process | |
| CN107704426A (en) | Water level prediction method based on extension wavelet-neural network model | |
| CN115742855A (en) | Electric automobile remaining mileage prediction method and device, electric automobile and medium | |
| CN109540089B (en) | Bridge deck elevation fitting method based on Bayes-Kriging model | |
| JP2002180295A (en) | Method and apparatus for analyzing electrodeposition coating | |
| CN107909202B (en) | Time sequence-based oil well liquid production integrated prediction method | |
| CN113111256A (en) | Production work order recommendation method based on depth knowledge map | |
| CN116303786B (en) | Block chain financial big data management system based on multidimensional data fusion algorithm | |
| JP2003049298A (en) | Method for estimating coating film thickness of real car, system for estimating coating film thickness of real car and recording medium | |
| CN115775156A (en) | Mine economy evaluation raw material price prediction method based on hybrid learning model | |
| JP2002257689A (en) | System for predicting corrosion phenomenon in vehicle, method used for the same, program used for the same, and computer-readable recording medium with program for the same stored therein | |
| Suzdaleva et al. | Recursive estimation of mixtures of exponential and normal distributions | |
| CN114239948A (en) | Deep traffic flow prediction method, medium and equipment based on time sequence decomposition unit | |
| JP2003041395A (en) | Analysis method using computer, analysis system, and recording medium | |
| JP4459698B2 (en) | Paint data generation method and computer-executable program for executing the generation method | |
| Ali et al. | The use of ARIMA, LSTM and GRU models in time series hybridization with practical application | |
| Sun et al. | Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models | |
| JP2007002323A (en) | Method for calculating using amount of electrodeposition paint | |
| CN115236978B (en) | Equivalent factor adjusting system and method based on predicted vehicle speed | |
| CN117851736B (en) | Meteorological element interpolation method based on fuzzy self-adaptive optimizing fusion | |
| CN114822025B (en) | Traffic flow combined prediction method | |
| Aqlani et al. | Comparative Analyisis of Software Cost Estimation Project using Algorithmic Method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20050310 |
|
| A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20060216 |
|
| A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20060227 |
|
| A521 | Written amendment |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20060404 |
|
| A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20060703 |
|
| A521 | Written amendment |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20060831 |
|
| A02 | Decision of refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A02 Effective date: 20061017 |
|
| A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 |
|
| A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20081113 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20111121 Year of fee payment: 3 |
|
| R150 | Certificate of patent or registration of utility model |
Free format text: JAPANESE INTERMEDIATE CODE: R150 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20121121 Year of fee payment: 4 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20121121 Year of fee payment: 4 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20131121 Year of fee payment: 5 |
|
| R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |
|
| S531 | Written request for registration of change of domicile |
Free format text: JAPANESE INTERMEDIATE CODE: R313531 |
|
| R350 | Written notification of registration of transfer |
Free format text: JAPANESE INTERMEDIATE CODE: R350 |
|
| R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |
|
| R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |
|
| S533 | Written request for registration of change of name |
Free format text: JAPANESE INTERMEDIATE CODE: R313533 |
|
| R350 | Written notification of registration of transfer |
Free format text: JAPANESE INTERMEDIATE CODE: R350 |
|
| R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |
|
| LAPS | Cancellation because of no payment of annual fees |